Jarvis1111

/

DoctorAgent-RL-SFT-1k-Thinking

like 1

This PR significantly enhances the model card for DoctorAgent-RL by:

• Updating the pipeline_tag from question-answering to text-generation to better reflect its multi-turn clinical dialogue capabilities.
• Adding library_name: transformers to ensure proper integration and discoverability on the Hugging Face Hub, enabling the "Use in Transformers" widget.
• Including the paper metadata tag linking to the official paper.
• Providing a comprehensive overview of the model based on the paper's abstract and the GitHub README.
• Adding direct links to the paper on Hugging Face, the GitHub repository, and the associated Hugging Face Collection.
• Incorporating key features and a diagram of the methodology.
• Providing a clear Python code snippet for using the model with the transformers library for multi-turn dialogue.
• Adding the appropriate citation information.